Commit Graph

3102 Commits

Author SHA1 Message Date
AUTOMATIC1111
72e81d5b6c
Merge pull request #5840 from stysmmaker/feat/xy-plot-new-axes
Add upscale latent, VAE, styles as new axis options to X/Y plot
2022-12-24 09:05:12 +03:00
AUTOMATIC
399b229783 eliminate duplicated code
add an option to samplers for skipping next to last sigma
2022-12-24 09:03:45 +03:00
AUTOMATIC1111
5667ec4ca7
Merge pull request #5797 from mcmonkey4eva/dpm2-a-fix
Add a workaround patch for DPM2 a issue
2022-12-24 08:51:43 +03:00
AUTOMATIC1111
0fdf368a54
Merge pull request #5894 from florianchrometz/patch-1
Set httpcore version in requirements - fixes #4833
2022-12-24 08:37:20 +03:00
AUTOMATIC1111
3bfc6c07ae
Merge pull request #5810 from brkirch/fix-training-mps
Training fixes for MPS
2022-12-24 08:34:46 +03:00
AUTOMATIC1111
f0dfed2a17
Merge pull request #5796 from brkirch/invoke-fix
Improve InvokeAI cross attention reliability and speed when using MPS for large images
2022-12-24 08:21:19 +03:00
AUTOMATIC1111
7115ab5d1e
Merge pull request #5617 from mcmonkey4eva/fix-hints-file
fix hints file typo
2022-12-24 08:16:04 +03:00
AUTOMATIC
0c747d4013 add a comment for disable xformers hack 2022-12-24 07:57:56 +03:00
AUTOMATIC1111
5ee75e3c1e
Merge pull request #5794 from Akegarasu/master
fix: xformers
2022-12-24 07:49:15 +03:00
Akiba
13e0295ab6
fix: xformers use importlib 2022-12-24 11:17:21 +08:00
brkirch
35b1775b32 Use other MPS optimization for large q.shape[0] * q.shape[1]
Check if q.shape[0] * q.shape[1] is 2**18 or larger and use the lower memory usage MPS optimization if it is. This should prevent most crashes that were occurring at certain resolutions (e.g. 1024x1024, 2048x512, 512x2048).

Also included is a change to check slice_size and prevent it from being divisible by 4096 which also results in a crash. Otherwise a crash can occur at 1024x512 or 512x1024 resolution.
2022-12-20 21:30:00 -05:00
Florian Chrometz
d050bb7863
Set httpcore version in requirements - fixes #4833 2022-12-20 20:19:50 +01:00
Philpax
22f1527fa7 feat(api): add override_settings_restore_afterwards 2022-12-20 20:36:49 +11:00
Alex "mcmonkey" Goodwin
7ba9bc2fdb fix dpm2 in img2img as well 2022-12-18 19:16:42 -08:00
MMaker
492052b5df
feat: Add upscale latent, VAE, styles to X/Y plot
Adds upscale latent space for hires., VAE, and Styles as new axis options to the X/Y plot.
2022-12-18 10:47:02 -05:00
Billy Cao
c02ef0f428 Fix PIL being imported before its installed (for new users only) 2022-12-18 20:51:59 +08:00
Billy Cao
35f0698ae8 Dirty fix for missing PIL supported file extensions 2022-12-18 20:45:30 +08:00
timntorres
6fd91c9179 Update OptionInfo to match preexisting option. 2022-12-17 08:59:02 -08:00
timntorres
a7a039d53a Add option to include upscaler name in filename. 2022-12-17 08:50:20 -08:00
timntorres
a26fe85056 Add upscaler name as a suffix. 2022-12-17 05:11:06 -08:00
brkirch
cca16373de Add attributes used by MPS 2022-12-17 04:23:08 -05:00
brkirch
16b4509fa6 Add numpy fix for MPS on PyTorch 1.12.1
When saving training results with torch.save(), an exception is thrown:
"RuntimeError: Can't call numpy() on Tensor that requires grad. Use tensor.detach().numpy() instead."

So for MPS, check if Tensor.requires_grad and detach() if necessary.
2022-12-17 04:22:58 -05:00
MMaker
b7c478c3eb
fix: Modify font size when unable to fit in plot
This prevents scenarios where text without line breaks will start overlapping with each other when generating X/Y plots. This is most evident when generating X/Y plots with checkpoints, as most don't contain spaces and sometimes include extra information such as the epoch, making it extra long.
2022-12-17 00:45:43 -05:00
Alex "mcmonkey" Goodwin
180fdf7809 apply to DPM2 (non-ancestral) as well 2022-12-16 08:42:00 -08:00
Alex "mcmonkey" Goodwin
8b0703b8fc Add a workaround patch for DPM2 a issue
DPM2 a and DPM2 a Karras samplers are both affected by an issue described by https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/3483 and can be resolved by a workaround suggested by the k-diffusion author at https://github.com/crowsonkb/k-diffusion/issues/43#issuecomment-1305195666
2022-12-16 08:18:29 -08:00
Akiba
35e1017e3e
fix: xformers 2022-12-16 20:43:09 +08:00
camenduru
9fd457e21d
allow_credentials and allow_headers for api
from https://fastapi.tiangolo.com/tutorial/cors/
2022-12-15 21:57:48 +03:00
Jim Hays
c0355caefe Fix various typos 2022-12-14 21:01:32 -05:00
Yuval Aboulafia
957e15c464 Correct singleton comparisons 2022-12-14 20:59:33 +02:00
space-nuko
5f407ebd61 Fix comment 2022-12-13 14:32:26 -08:00
space-nuko
1fcb959514 Correctly restore default hypernetwork strength 2022-12-13 14:30:54 -08:00
space-nuko
9d5948e5f7 Correctly restore hypernetwork from hash 2022-12-13 14:25:16 -08:00
space-nuko
7077428209 Save hypernetwork hash in infotext 2022-12-13 13:05:40 -08:00
David Vorick
27c0504bc4
add support for prompts, negative prompts, and sampler-by-name in text file script 2022-12-13 12:03:16 -05:00
Fionn Langhans
cb64439f41
Bugfix: Use /usr/bin/env bash instead of just /bin/bash
The problem: Some Linux distrubutions, like NixOS, use a
non-standard filesystem. This causes the bash program to not
be at /bin/bash (though /usr/bin/env is always there).
2022-12-12 21:27:46 +01:00
ThereforeGames
9bcf4165f8
Update requirements.txt 2022-12-11 18:09:18 -05:00
ThereforeGames
9170224d23
Delete venv/Lib/site-packages directory 2022-12-11 18:06:22 -05:00
ThereforeGames
2e8b5418e3
Improve color correction with luminosity blend 2022-12-11 18:03:36 -05:00
ThereforeGames
00ca6a6db4
Add files via upload 2022-12-11 17:59:59 -05:00
Dean Hopkins
960293d6b2
API endpoint to refresh checkpoints
API endpoint to refresh checkpoints
2022-12-11 19:16:44 +00:00
MrCheeze
ec0a48826f unconditionally set use_ema=False if value not specified (True never worked, and all configs except v1-inpainting-inference.yaml already correctly set it to False) 2022-12-11 11:18:34 -05:00
Dean van Dugteren
59c6511494
fix: fallback model_checkpoint if it's empty
This fixes the following error when SD attempts to start with a deleted checkpoint:

```
Traceback (most recent call last):
  File "D:\Web\stable-diffusion-webui\launch.py", line 295, in <module>
    start()
  File "D:\Web\stable-diffusion-webui\launch.py", line 290, in start
    webui.webui()
  File "D:\Web\stable-diffusion-webui\webui.py", line 132, in webui
    initialize()
  File "D:\Web\stable-diffusion-webui\webui.py", line 62, in initialize
    modules.sd_models.load_model()
  File "D:\Web\stable-diffusion-webui\modules\sd_models.py", line 283, in load_model
    checkpoint_info = checkpoint_info or select_checkpoint()
  File "D:\Web\stable-diffusion-webui\modules\sd_models.py", line 117, in select_checkpoint
    checkpoint_info = checkpoints_list.get(model_checkpoint, None)
TypeError: unhashable type: 'list'
```
2022-12-11 17:08:51 +01:00
repligator
d5a9de1662
Update hints.js - DPM adaptive
Added mouse-over for DPM adaptive
2022-12-11 09:39:56 -05:00
Alex "mcmonkey" Goodwin
7b0a28f8ee fix hints file typo 2022-12-11 02:17:14 -08:00
Bwin4L
303df25cc2
Make the generated image count only count new images in the currently active tab 2022-12-10 22:58:06 +01:00
wywywywy
8bcdd50461 Add safetensors support to LDSR 2022-12-10 18:57:18 +00:00
MrCheeze
bd81a09eac fix support for 2.0 inpainting model while maintaining support for 1.5 inpainting model 2022-12-10 11:29:26 -05:00
MrCheeze
a1c8ad8828 unload depth model if medvram/lowvram enabled 2022-12-10 11:02:47 -05:00
AUTOMATIC1111
685f9631b5
Merge pull request #5586 from wywywywy/ldsr-improvements
LDSR improvements - cache / optimization / opt_channelslast
2022-12-10 18:22:39 +03:00
AUTOMATIC1111
0a81dd5225
Merge pull request #5585 from Bwin4L/master
Fix token counter color on dark theme
2022-12-10 18:20:28 +03:00